Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FileChooser
    -0.08
     balancing
    -0.07
     haste
    -0.07
    _RENDERER
    -0.07
    خت
    -0.06
    /dat
    -0.06
     breastfeeding
    -0.06
    /day
    -0.06
    乾
    -0.06
     souhlas
    -0.06
    POSITIVE LOGITS
     destroyed
    0.06
     Workflow
    0.06
     ')↵
    0.06
     Missing
    0.06
     právní
    0.06
    ский
    0.06
    anten
    0.06
    เร
    0.06
    lico
    0.06
     destroy
    0.06
    Act Density 0.002%

    No Known Activations